© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 35943
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables related to equations and summations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical notation with subscripted variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.65
     ♥
    -0.63
     estekak
    -0.61
    
    -0.60
     queſta
    -0.60
    dafx
    -0.60
     محفوظة
    -0.60
     Numerade
    -0.60
    ReusableCell
    -0.60
    <unused30>
    -0.59
    POSITIVE LOGITS
     noastre
    0.41
     independientes
    0.41
     indépendante
    0.40
     lámpara
    0.40
     mármol
    0.36
     correspondiente
    0.36
     éste
    0.36
     acento
    0.36
     indépendant
    0.35
     brasileño
    0.35
    Activations Density 1.710%

    No Known Activations